Rule-based Morphological Inflection Improves Neural Terminology Translation

TL;DR

This paper presents a modular framework for incorporating lemma constraints into neural machine translation, utilizing rule-based and neural inflection modules to improve translation accuracy in low-resource and domain adaptation scenarios.

Contribution

It introduces a novel cross-lingual inflection module that effectively integrates lemma constraints into NMT, with a focus on rule-based approaches for better performance and lower costs.

Findings

Rule-based inflection module outperforms neural inflection in accuracy.

The framework improves constraint incorporation in low-resource settings.

Lower training costs compared to end-to-end approaches.

Abstract

Current approaches to incorporating terminology constraints in machine translation (MT) typically assume that the constraint terms are provided in their correct morphological forms. This limits their application to real-world scenarios where constraint terms are provided as lemmas. In this paper, we introduce a modular framework for incorporating lemma constraints in neural MT (NMT) in which linguistic knowledge and diverse types of NMT models can be flexibly applied. It is based on a novel cross-lingual inflection module that inflects the target lemma constraints based on the source context. We explore linguistically motivated rule-based and data-driven neural-based inflection modules and design English-German health and English-Lithuanian news test suites to evaluate them in domain adaptation and low-resource MT settings. Results show that our rule-based inflection module helps NMT models incorporate lemma constraints more accurately than a neural module and outperforms the existing end-to-end approach with lower training costs.